Chat Ask

Chat and ask functionality for OpenClaw

Security Scan

The skill's code, instructions, and requirements match its stated purpose (simple chat, ask, and in-memory history) and do not request extra credentials or perform suspicious actions.

Purpose & Capability

Name/description, required binaries (python3), and included scripts all align: the skill implements chat, ask, and chat-history tools with no unrelated dependencies or requested credentials.

Instruction Scope

SKILL.md directs the agent to run the provided python scripts. The scripts operate on input arguments and an in-memory history, do not read sensitive system files, do not call external endpoints, and do not access environment variables beyond normal runtime.

Install Mechanism

No install specification is provided (instruction-only). The shipped code is executed by python3 directly; there are no downloads, package installs, or archive extraction steps.

Credentials

The skill requests no environment variables or credentials. The functionality implemented does not appear to need any secrets or external service credentials.

Persistence & Privilege

The skill is not always-enabled and does not modify other skills or system-wide settings. Chat history is kept only in-memory (no persistent storage or added privileges).

Assessment

This skill appears coherent and minimal: it runs local Python scripts to provide chat/ask functionality and keeps history only in-memory. Before installing, consider: (1) this provides no persistent storage — if you need persistence you'll have to add a database (which would require credentials); (2) the scripts write logs to stderr and output JSON to stdout (these outputs may be captured by hosting environments); (3) review the shipped Python files if you run this in a shared/multi-tenant environment to ensure they meet your privacy requirements. There are no environment variable requests, network calls, or obvious exfiltration behaviors in the provided code.

Chat/Ask Skill

A simple skill for handling chat conversations and Q&A with OpenClaw.

Description

This skill provides tools for:

• Chat conversations with OpenClaw
• Asking questions and getting answers
• Managing chat history
• Simple conversation analysis

Tools

chat

Start or continue a chat conversation.

Parameters:

• message (string): The message to send in chat
• context (string, optional): Additional context for the conversation

Example:

{
  "message": "Hello, how are you?",
  "context": "Just checking in"
}

ask

Ask a question to OpenClaw.

Parameters:

• question (string): The question to ask
• detailed (boolean, optional): Whether to provide a detailed answer (default: false)

Example:

{
  "question": "What is the weather like?",
  "detailed": true
}

chat-history

Manage chat history.

Parameters:

• action (string): Action to perform - 'get', 'clear', or 'summary'
• limit (number, optional): Number of messages to retrieve (default: 10)

Example:

{
  "action": "get",
  "limit": 5
}

Usage

1. Start a chat:

   Use the chat tool to start a conversation
   

2. Ask questions:

   Use the ask tool for specific questions
   

3. Manage history:

   Use chat-history to review or clear conversations
   

How to Call Tools

chat tool

python3 scripts/chat_tool.py '<message>' '[context]'

Example:

python3 scripts/chat_tool.py 'Hello, how are you?' 'Just checking in'

ask tool

python3 scripts/ask_tool.py '<question>' [detailed]

Example:

python3 scripts/ask_tool.py 'What is OpenClaw?' true

chat_history tool

python3 scripts/chat_history_tool.py '<action>' [limit]

Examples:

# Get last 10 messages
python3 scripts/chat_history_tool.py 'get' 10

# Clear history
python3 scripts/chat_history_tool.py 'clear'

# Get summary
python3 scripts/chat_history_tool.py 'summary'

Response Format

All tools return JSON with:

• status: "success" or "error"
• timestamp: ISO format timestamp
• tool: Tool name that was called
• Additional tool-specific fields

chat response

{
  "status": "success",
  "response": "I received your message...",
  "timestamp": "2026-03-16T14:30:00.000Z",
  "tool": "chat"
}

ask response

{
  "status": "success",
  "answer": "OpenClaw is a self-hosted AI assistant...",
  "detailed": true,
  "timestamp": "2026-03-16T14:30:00.000Z",
  "tool": "ask"
}

chat_history response

{
  "status": "success",
  "action": "get",
  "history": [...],
  "count": 5,
  "limit": 10,
  "total": 15
}

Configuration

No special configuration required. The skill works out of the box.

Notes

• Chat history is stored in memory during the session
• For persistent storage, consider integrating with a database
• The skill is designed for simple conversational interactions